3 papers
cs.LG2026
LSTM VS. Feed-Forward Autoencoders for Unsupervised Fault Detection in Hydraulic Pumps
P. Sánchez, K. Reyes, B. Radu +1
Unplanned failures in industrial hydraulic pumps can halt production and incur substantial costs. We explore two unsupervised autoencoder (AE) schemes for early fault detection: a…
cs.LG2026
Assesing the Viability of Unsupervised Learning with Autoencoders for Predictive Maintenance in Helicopter Engines
P. Sánchez, K. Reyes, B. Radu +1
Unplanned engine failures in helicopters can lead to severe operational disruptions, safety hazards, and costly repairs. To mitigate these risks, this study compares two predictive…
cs.LG2026
Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders
P. Sánchez, K. Reyes, B. Radu +1
This paper introduces an unsupervised health-monitoring framework for turbofan engines that does not require run-to-failure labels. First, operating-condition effects in NASA CMAPS…